openspec-explore

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agent/skills/openspec-explore/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body conveys a coherent, well-organized behavioral stance with genuinely concrete anchors (commands, artifact paths, capture table, example dialogues). Its weaknesses are redundancy across the stance, entry-points, and guardrails sections, an oversized inline example gallery with no bundle files, and an intentionally loose workflow that leaves checkpoints implicit.

Suggestions

Consolidate the duplicated rules: state the never-implement, don't-auto-capture, and do-visualize guidance once (e.g., keep only the Guardrails section) and trim the rest.

Move the four 'Handling Different Entry Points' ASCII dialogue examples into a references/ file (e.g., examples.md) and keep one short inline example plus a clearly signaled pointer, cutting SKILL.md substantially.

Tighten the workflow around the opening context check: make the change-exists / no-change branch and the optional capture step an explicit short sequence so the flow is unambiguous even though the mode is a stance.

Dimension	Reasoning	Score
Conciseness	The body mostly avoids explaining things Claude already knows, but it repeats key rules across sections - "NEVER write code" appears in both the IMPORTANT block and Guardrails, and "don't auto-capture" and "do visualize" are each stated twice - and the four ASCII dialogue examples run roughly 100 lines. It fits 'mostly efficient but could be tightened' rather than the 4 anchor's 'minor instances'.	3 / 5
Actionability	Provides concrete, executable elements - the `openspec list --json` command, exact artifact paths like `openspec/changes/<name>/proposal.md`, a capture-destination table, and example offer phrasings - but a substantial portion is stance description rather than executable guidance, so it stops short of fully copy-paste-ready.	4 / 5
Workflow Clarity	There is an explicit opening check (`openspec list --json`) with a two-way branch (change exists / doesn't) and a numbered 4-step sequence for the change-exists path, but the skill is deliberately 'a stance, not a workflow', so sequencing beyond the entry check is implicit and no validation checkpoints exist. This matches 'steps listed but validation gaps; checkpoints missing or implicit' rather than the 4 anchor's 'clear sequence with most checkpoints'.	3 / 5
Progressive Disclosure	Section headers are clear and well-organized, but there are no bundle files at all: the ~100-line entry-point example gallery and the insight-capture table are inlined in a single 290-line SKILL.md where they could live in a reference file. This matches 'some structure but could be better organized; content that should be separate is inline'.	3 / 5
	Total	13 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly covers what the skill does and when to use it, with a natural trigger phrase. Its main gaps are slightly abstract capability wording and missing common synonyms a user might say when they want a thinking partner.

Suggestions

Add common trigger variations users would naturally say, such as 'brainstorm', 'talk through', or 'discuss options', to the Use when clause.

Make the capabilities slightly more concrete, e.g. 'explores ideas, investigates the codebase, compares options, and clarifies requirements' to sharpen what the skill actually does.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions - "exploring ideas, investigating problems, and clarifying requirements" - which goes beyond naming the domain, but the actions are somewhat high-level and not comprehensive, matching the 'several specific actions; minor gaps' anchor rather than the full-coverage 5.	4 / 5
Completeness	Clearly answers both: what ("a thinking partner for exploring ideas, investigating problems, and clarifying requirements") and when ("Use when the user wants to think through something before or during a change") with an explicit trigger clause. The when-clause is explicit and concrete, so it fits the 5 anchor rather than the 4 anchor where the when 'could be more explicit'.	5 / 5
Trigger Term Quality	"think through something" is a natural user phrase and "exploring"/"investigating" are relevant keywords, but common variations users would actually say ("brainstorm", "talk through", "discuss options") are missing, matching 'good keyword coverage; a few natural terms missing'.	4 / 5
Distinctiveness Conflict Risk	The "explore mode" / thinking-partner framing before or during a change is a fairly distinct niche with clear triggers, but broad overlap risk remains with generic discussion or brainstorming skills, matching 'mostly distinct; minor overlap risk'.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Draculabo/AntigravityManager
Path: .agent/skills/openspec-explore/SKILL.md
Commit: ccea788

Reviewed: 14 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.